相关论文: Simple dynamic word embeddings for mapping percept…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Verbs occur in different syntactic environments, or frames. We investigate whether artificial neural networks encode grammatical distinctions necessary for inferring the idiosyncratic frame-selectional properties of verbs. We introduce five…

Word embeddings are an essential instrument in many NLP tasks. Most available resources are trained on general language from Web corpora or Wikipedia dumps. However, word embeddings for domain-specific language are rare, in particular for…

Contextual adaptation in token embeddings plays a central role in determining how well language models maintain coherence and retain semantic relationships over extended text sequences. Static embeddings often impose constraints on lexical…

Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly…

In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT)…

Recent studies have introduced methods for learning acoustic word embeddings (AWEs)---fixed-size vector representations of words which encode their acoustic features. Despite the widespread use of AWEs in speech processing research, they…

Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply…

We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described…

Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using…

A common paradigm for identifying semantic differences across social and temporal contexts is the use of static word embeddings and their distances. In particular, past work has compared embeddings against "semantic axes" that represent two…

Artificial intelligence and machine learning are in a period of astounding growth. However, there are concerns that these technologies may be used, either with or without intention, to perpetuate the prejudice and unfairness that…

The meaning of a word is closely linked to sociocultural factors that can change over time and location, resulting in corresponding meaning changes. Taking a global view of words and their meanings in a widely used language, such as…

We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of…

To extract essential information from complex data, computer scientists have been developing machine learning models that learn low-dimensional representation mode. From such advances in machine learning research, not only computer…

We present hash embeddings, an efficient method for representing words in a continuous vector form. A hash embedding may be seen as an interpolation between a standard word embedding and a word embedding created using a random hash function…

There is an escalating need for methods to identify latent patterns in text data from many domains. We introduce a new method to identify topics in a corpus and represent documents as topic sequences. Discourse Atom Topic Modeling draws on…

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…